CN117768923B - New energy automobile data transmission optimization method and system based on 5G short-cut private network - Google Patents
New energy automobile data transmission optimization method and system based on 5G short-cut private network Download PDFInfo
- Publication number
- CN117768923B CN117768923B CN202410197083.1A CN202410197083A CN117768923B CN 117768923 B CN117768923 B CN 117768923B CN 202410197083 A CN202410197083 A CN 202410197083A CN 117768923 B CN117768923 B CN 117768923B
- Authority
- CN
- China
- Prior art keywords
- new energy
- energy automobile
- data
- data transmission
- transmission
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 169
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000005457 optimization Methods 0.000 title claims abstract description 21
- 230000002159 abnormal effect Effects 0.000 claims abstract description 25
- 230000008569 process Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 230000001133 acceleration Effects 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 239000006227 byproduct Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Landscapes
- Mobile Radio Communication Systems (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The invention relates to the technical field of data transmission. More particularly, the invention relates to a new energy automobile data transmission optimization method and system based on a 5G short-slice private network. The method comprises the following steps: selecting an optimal edge node corresponding to the data of each new energy automobile; transmitting data of each new energy automobile through a corresponding optimal edge node; in the real-time transmission process, the running state of each new energy automobile is monitored by using the new energy automobile fault prediction model, and the data transmission frequency of each new energy automobile is respectively adjusted according to the running state of each new energy automobile, so that the data transmission frequency of the new energy automobile with abnormal running state is increased, and the data transmission frequency of the new energy automobile with normal running state is reduced. The method can improve the rationality of the data transmission of the new energy automobile and timely monitor the fault state of the new energy automobile.
Description
Technical Field
The present invention relates generally to the field of data transmission technology. More particularly, the invention relates to a new energy automobile data transmission optimization method and system based on a 5G short-slice private network.
Background
The 5G short slice technique is one of the key techniques for 5G communication. Based on virtualization technology, the existing physical network is subjected to service logic segmentation to form an independent service logic network, and network services with mutually isolated and negotiable management functions and customized functions are provided for industries with different service requirements. The device (core, bearing, user plane, access, base station) slices are isolated and logically independent, and when any slice and the network linked by the slice fail, other slices and virtual networks to which the slice belongs are not affected. The slicing is similar to the virtual private network (Virtual Private Network, VPN) virtual channel application starting point of the traditional network, and the aim is to open up a relatively independent safe and quick channel for the private network applied on the public network, thereby realizing the organic recombination of the private network application requirement and the public network 5G network. Compared with the traditional data transmission method, the data transmission method based on the 5G short slice has many advantages, such as adopting a special channel for transmission, high safety, difficult leakage and reduced transmission cost; meanwhile, the special channel is used for transmission, no blockage is formed, and the reliability of transmission is enhanced.
With the development of communication technology, radiation is continuously emitted to other applications. For example, in the field of new energy automobiles, in order to ensure the efficiency of data transmission, a 5G short-slice private network is generally selected for transmission when transmitting operation data of the new energy automobiles. However, in the prior art, when the data of the new energy automobiles are transmitted by using the 5G short-slice private network, if there are a plurality of new energy automobiles, all the running data of all the new energy automobiles are transmitted periodically according to a certain frequency without distinction, so that the problem of redundant transmission data is caused; in addition, as the data volume transmitted by the edge node each time has a certain upper limit, the problem of low transmission efficiency can be caused, and in addition, when a certain new energy automobile fails, the failure cause of the new energy automobile can not be timely monitored, so that the failure cause can not be analyzed.
Disclosure of Invention
To solve one or more of the above-described technical problems, the present invention provides aspects as follows.
In a first aspect, the invention provides a new energy automobile data transmission optimization method based on a 5G short-slice private network, which comprises the following steps: selecting an optimal edge node corresponding to the data of each new energy automobile according to the distance between each new energy automobile and each edge node and the real-time transmission task quantity of each edge node, and transmitting the data of the new energy automobile through the corresponding optimal edge node; transmitting data of each new energy automobile through a corresponding optimal edge node; in the real-time transmission process, the running state of each new energy automobile is monitored by using a new energy automobile fault prediction model, and the data transmission frequency of each new energy automobile is respectively adjusted according to the running state of each new energy automobile so as to increase the data transmission frequency of the new energy automobile with abnormal running state and reduce the data transmission frequency of the new energy automobile with normal running state, wherein the new energy automobile fault prediction model is used for acquiring the running normal probability and the running abnormal probability of the new energy automobile according to each index data of the new energy automobile.
In one embodiment, for a new energy automobile, the method for determining the best edge node of the new energy automobile is to calculate the mismatching degree between the new energy automobile and each edge node, and select the edge node with the smallest mismatching degree as the best edge node of the new energy automobile, wherein the calculation expression of the mismatching degree is as follows:
In the method, in the process of the invention, Representing the degree of mismatch,/>Representing the distance between the ith new energy automobile and the jth edge transmission node,/>Representing the real-time transmission task amount of the jth edge node.
In one embodiment, the method for constructing the new energy automobile fault prediction model includes:
Collecting operation data of each moment in the history operation process of the new energy automobile, and labeling the operation data of each moment so as to obtain a new energy automobile operation data set; the labels comprise two labels of normal running and abnormal running of the new energy vehicle; the operation data comprise various index data of the new energy automobile;
training the neural network model by using the new energy vehicle running data set until the model reaches the set maximum training times or the loss is smaller than the set loss threshold value, and selecting the optimal model as the new energy vehicle fault prediction model according to the accuracy of model prediction.
In one embodiment, the index data includes: battery system data, motor data, and vehicle speed and acceleration during operation of the vehicle.
In one embodiment, the adjusting the data transmission frequency of each new energy automobile includes: according to the initial data transmission frequency of the new energy automobile, the normal running probability of the new energy automobile and the abnormal running probability of the new energy automobile, the new data transmission frequency f of the new energy automobile is determined, and the calculation expression is as follows:
In the method, in the process of the invention, Representing the initial transmission frequency,/>Representing the probability of abnormal operation of a new energy automobile output by a neural network,/>And the probability that the new energy automobile output by the neural network runs normally is represented.
In one embodiment, further comprising: if at a certain moment, data of a plurality of new energy automobiles are transmitted through the same edge node at the same time, analyzing the history of data transmission for the edge node to obtain the optimal data transmission quantity of the edge node, calculating the total quantity of the transmissible data of each new energy automobile according to the optimal data transmission quantity and the number of the new energy automobiles transmitting the data through the edge node, and enabling the data of the new energy automobiles transmitted each time not to exceed the total quantity of the corresponding transmissible data; the calculation expression of the total amount of the transmissible data of the new energy automobile is as follows:
Wherein, Representing the total amount of transmissible data of the ith new energy automobile,/>Representing the optimal data traffic of the jth edge transmission node,/>And the number of the new energy automobiles transmitted by the jth edge transmission node is represented.
In one embodiment, for a new energy vehicle, after transmitting all the corresponding index data once, the index data with the highest priority is transmitted once again.
In one embodiment, the method for determining the transmission priority of the index data is: and acquiring the importance degree of each index on the normal operation of the new energy automobile based on the new energy automobile fault prediction model, wherein the higher the importance degree is, the higher the corresponding transmission priority is, and the importance degree of each index on the normal operation of the new energy automobile is acquired through a cam algorithm.
In one embodiment, obtaining the optimal data transfer amount for the edge node comprises: clustering the transmission quality of the historical data of the edge nodes, so as to obtain clusters with good transmission quality and clusters with poor transmission quality; and calculating the average value of the data quantity transmitted each time in the cluster with good transmission quality, thereby obtaining the optimal data transmission quantity of the edge node.
In a second aspect, the invention provides a new energy automobile data transmission optimization system based on a 5G short-cut private network, which comprises a memory and a processor, wherein computer instructions are stored in the memory, and when the computer program instructions are executed by the processor, the new energy automobile data transmission optimization method based on the 5G short-cut private network is realized.
The invention has the technical effects that: according to the new energy automobile data transmission optimization method based on the 5G short-cut private network, when the 5G short-cut private network is utilized to transmit the new energy automobile data, the data transmission frequencies of all the new energy automobiles are not indiscriminately kept consistent, but the running state of each new energy automobile is monitored in real time in the transmission process, the data transmission frequency of the new energy automobile is dynamically adjusted according to the running state of each new energy automobile, so that the data transmission frequency of the new energy automobile with abnormal running state is improved, the data transmission frequency of the new energy automobile with normal running state is reduced, and the fault state of the new energy automobile can be timely monitored, so that the fault cause of the new energy automobile can be analyzed.
In some special cases, the situation that data loss may occur when data of each index is transmitted, the method of the invention does not transmit all index data of the new energy automobile according to the same transmission frequency when the running data of the new energy automobile is transmitted, but considers the total amount of transmissible data of a data transmission channel and the transmission priority of each index data, the higher the transmission priority index data is, the higher the importance degree of the index data on the safety of the new energy automobile is, the data with the highest transmission priority is transmitted twice more, and the data with the highest transmission priority is transmitted once more, thereby ensuring that the important index data can be reliably transmitted, and further ensuring that the fault state of the new energy automobile can be timely monitored
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. In the drawings, embodiments of the invention are illustrated by way of example and not by way of limitation, and like reference numerals refer to similar or corresponding parts and in which:
Fig. 1 is a flowchart schematically illustrating a new energy vehicle data transmission optimization method based on a 5G short-slice private network according to an embodiment of the present invention;
FIG. 2 is a flow chart schematically illustrating a method of constructing a new energy automobile fault prediction model in accordance with an embodiment of the present invention;
FIG. 3 is a schematic diagram schematically illustrating a secondary index data transmission mode according to an embodiment of the present invention;
FIG. 4 is a flow chart schematically illustrating a method of acquiring an optimal data traffic volume for an edge node according to an embodiment of the present invention;
Fig. 5 is a schematic diagram schematically illustrating a new energy automobile data transmission optimization system based on a 5G short-slice private network according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.
New energy automobile data transmission optimization method embodiment based on 5G short-slice private network:
as shown in fig. 1, the new energy automobile data transmission optimization method based on the 5G short-slice private network of the present invention includes:
S101, selecting an optimal edge node, which specifically comprises the following steps: selecting an optimal edge node corresponding to the data of each new energy automobile according to the distance between each new energy automobile and each edge node and the real-time transmission task quantity of each edge node, and transmitting the data of the new energy automobile through the corresponding optimal edge node;
In general, for a new energy automobile, data of the new energy automobile needs to be transmitted by selecting an edge node closest to the new energy and having enough free transmission space, for example: for a new energy automobile, the method for determining the optimal edge node of the new energy automobile comprises the steps of firstly calculating the mismatching degree of the new energy automobile and each edge node, and selecting the edge node with the smallest mismatching degree as the optimal edge node, wherein the calculation expression of the mismatching degree is as follows:
（1）
In the method, in the process of the invention, Representing the degree of mismatch,/>Representing the distance between the ith new energy automobile and the jth edge transmission node,/>Representing the real-time transmission task amount of the jth edge node.
The edge nodes comprise edge side product forms such as edge gateways, edge controllers, edge servers and the like. The edge side product form has the functions of edge side real-time data analysis, local data storage, real-time network connection and the like.
S102, dynamically adjusting the data transmission frequency of each new energy automobile, wherein the data transmission frequency is specifically as follows: the data of each new energy automobile is transmitted through a corresponding optimal edge node, the running state of each new energy automobile is monitored by utilizing a new energy automobile fault prediction model in the real-time transmission process, and the data transmission frequency of each new energy automobile is respectively adjusted according to the running state of each new energy automobile, so that the data transmission frequency of the new energy automobile with abnormal running state is increased, and the data transmission frequency of the new energy automobile with normal running state is reduced; the new energy automobile fault prediction model is used for acquiring the probability of normal operation and the probability of abnormal operation of the new energy automobile according to various index data of the new energy automobile.
The new energy automobile fault prediction model can adopt a neural network model, a gray prediction model, a time sequence model, a logistic regression model, a linear regression model, a random forest model or other suitable prediction models.
And respectively inputting the transmitted data of each index of each new energy automobile into a new energy automobile fault prediction model, namely obtaining the normal running probability and abnormal running (i.e. fault) probability of each new energy automobile at the corresponding moment, and when the abnormal running probability is greater than a preset threshold value, indicating that the monitoring result is that the running state of the new energy automobile at the corresponding moment is a fault state.
In the process of transmitting the data of the new energy automobiles, the initial transmission frequency of the operation data of each new energy automobile is generallyThe system is fixed, but in actual conditions, the running state of each new energy vehicle is different, and when the running state of the new energy vehicle is abnormal, the transmission frequency of the running data of the new energy vehicle is increased so as to better analyze the cause of faults. Therefore, by increasing the data transmission frequency of the new energy automobile with abnormal running state and reducing the data transmission frequency of the new energy automobile with normal running state, the running data of the new energy automobile can be timely detected when the new energy automobile fails, and therefore the failure cause of the new energy automobile is analyzed.
According to the new energy automobile data transmission optimization method based on the 5G short-cut private network, when the 5G short-cut private network is utilized to transmit the new energy automobile data, the data transmission frequencies of all the new energy automobiles are not indiscriminately kept consistent, but the running state of each new energy automobile is monitored in real time in the transmission process, the data transmission frequency of the new energy automobile is dynamically adjusted according to the running state of each new energy automobile, so that the data transmission frequency of the new energy automobile with abnormal running state is improved, the data transmission frequency of the new energy automobile with normal running state is reduced, and the fault state of the new energy automobile can be timely monitored, so that the fault cause of the new energy automobile can be analyzed.
In one embodiment, the new energy automobile fault prediction model adopts a neural network model, as shown in fig. 2, and the method for constructing the new energy automobile fault prediction model comprises the following steps:
S201, acquiring a new energy automobile operation data set, which specifically comprises the following steps: collecting operation data of each moment in the history operation process of the new energy automobile, and labeling the operation data of each moment so as to obtain a new energy automobile operation data set; the labels comprise two labels of normal running and abnormal running of the new energy vehicle; the operation data comprise data of various indexes of the new energy automobile.
The collected operation data comprise various index data in the operation process of the new energy automobile, such as battery system data, motor data, and automobile speed, acceleration and the like in the operation process of the automobile. The battery system data comprises battery voltage, charge-discharge current and single battery temperature; the motor data includes temperature, rotational speed, operating voltage, operating current, etc. of the motor. These data can be obtained by corresponding sensors.
S202, training a new energy automobile fault prediction model, wherein the new energy automobile fault prediction model specifically comprises the following steps: training the neural network model by using the new energy automobile operation data set until the model reaches the set maximum training times or the loss is smaller than the set loss threshold value, and selecting the optimal model as the new energy automobile fault prediction model according to the model prediction accuracy.
The loss function of the neural network model adopts a cross entropy loss function, and a gradient descent algorithm is used in training.
In one embodiment, the adjusting the data transmission frequency of each new energy automobile includes: according to the initial data transmission frequency of the new energy automobile, the normal running probability of the new energy automobile and the abnormal running probability of the new energy automobile, the new data transmission frequency f of the new energy automobile is determined, and the calculation expression is as follows:
（2）
In the method, in the process of the invention, Representing the initial transmission frequency,/>Representing the probability of abnormal operation of a new energy automobile output by a neural network,/>And the probability that the new energy automobile output by the neural network runs normally is represented.
If there are multiple new energy vehicles transmitting data through the same edge node at a time, if the data transmission amount of each new energy vehicle is too large, the line may be jammed, and further the data of other new energy vehicles cannot be normally transmitted, so as to ensure the data transmission quality, in an embodiment, the method further includes: if at a certain moment, data of a plurality of new energy automobiles are transmitted through the same edge node at the same time, analyzing the history of data transmission for the edge node to obtain the optimal data transmission quantity of the edge node, calculating the total quantity of the transmissible data of each new energy automobile according to the optimal data transmission quantity and the number of the new energy automobiles transmitting the data through the edge node, and enabling the data of the new energy automobiles transmitted each time not to exceed the total quantity of the corresponding transmissible data; the calculation expression of the total amount of transmissible data of each new energy automobile is as follows:
（3）
Wherein, Representing the total amount of transmissible data of the ith new energy automobile,/>Representing the optimal data traffic of the jth edge transmission node,/>And the number of the new energy automobiles transmitted by the jth edge transmission node is represented.
After the total amount of the transmissible data of each new energy automobile is calculated, the transmitted index data can be selected according to the order of the transmission priority from high to low on the premise that the transmission data amount does not exceed the total amount of the transmissible data of each new energy automobile.
The condition of the historical transmission data comprises the data quantity and the data transmission quality transmitted at each time of the history, wherein the data transmission quality can be evaluated according to the data transmission speed, whether the data is interfered in the transmission process, whether the data is distorted, whether the data is lost and whether the data is lost. The optimal data transmission quantity of the edge node can be determined by analyzing the data quantity and the data transmission quality transmitted at each moment; when the data transmission amount is the optimal data transmission amount, the data transmission efficiency and the data transmission quality can be ensured.
And a certain bandwidth is allocated for each new energy automobile by calculating the total amount of transmissible data of each new energy automobile, so that the problems of congestion of a transmission line and low data transmission efficiency caused by overlarge data transmission amount are avoided.
In one embodiment, for a new energy vehicle, after transmitting all the corresponding index data once, the index data with the highest priority is transmitted once again.
As shown in fig. 3, assuming that the data of the new energy automobile includes three index data, which are respectively X index data, Y index data, and Z index data, wherein the priority of the X index data is greater than the priority of the Y index data, and the priority of the Y index data is greater than the priority of the Z index data, the X index data is transmitted twice in the time slot of the new energy automobile.
Under certain special conditions, the situation that data is lost possibly occurs when the data of each index is transmitted, all index data of the new energy automobile are not transmitted according to the same transmission frequency when the operation data of the new energy automobile are transmitted, the index data with higher transmission priority is considered, the importance degree of the index data for the safety of the new energy automobile is higher, the data with highest transmission priority is transmitted twice more, and the data with second highest transmission priority is transmitted once more, so that the important index data can be reliably transmitted, and the fault state of the new energy automobile can be timely monitored.
In one embodiment, the method for determining the transmission priority of the index data is: and acquiring the importance degree of each index on the normal operation of the new energy automobile based on the new energy automobile fault prediction model, wherein the higher the importance degree is, the higher the corresponding transmission priority is. And a cam algorithm can be adopted to obtain the importance degree of each index data on the normal operation of the new energy automobile. The cam algorithm is a feature visualization technology, and can calculate the contribution distribution of input features to the output of a prediction model, namely the importance degree of various input features. The input of the new energy automobile fault prediction model is various index data of the new energy automobile, and the importance degree of various indexes on the safety of the new energy automobile can be obtained by adopting a cam algorithm.
If the importance degree of a certain index on the normal operation of the new energy automobile is high, the influence degree of the data corresponding to the index on the normal operation of the new energy automobile is high, the data corresponding to the index can cause the abnormal operation of the new energy automobile to be high once abnormal, and in order to timely monitor the abnormal operation state of the new energy automobile, the important index data is required to be monitored in the automobile running.
As can be seen from the above embodiments, the optimal data transmission amount of the edge node can be obtained by analyzing the historical transmission data of the edge node, as shown in fig. 4, and in one embodiment, obtaining the optimal data transmission amount of the edge node includes:
S301, clustering the transmission quality of the historical data of the edge nodes, so as to obtain clusters with good transmission quality and clusters with poor transmission quality;
the clustering algorithm may employ K-means clustering, mean shift clustering, density-based clustering methods, or other suitable clustering algorithms.
S302, calculating the average value of the data quantity transmitted each time in the cluster with good transmission quality, thereby obtaining the optimal data transmission quantity of the edge node.
For example: 3 times of data are transmitted in the cluster with good transmission quality, the data quantity of the first transmission is a, the data quantity of the second transmission is b, the data quantity of the third transmission is c, and the average value of the data quantity of each transmission of the cluster with good transmission quality is (a+b+c)/3, and the average value is used as the optimal data transmission quantity of the edge node.
New energy automobile data transmission optimization system embodiment based on 5G short-slice private network:
The invention also provides a new energy automobile data transmission optimization system based on the 5G short-slice private network. As shown in fig. 5, the new energy automobile data transmission optimization system based on the 5G short-slice private network includes a processor and a memory, where the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the new energy automobile data transmission optimization method based on the 5G short-slice private network according to the first aspect of the present invention is implemented.
The new energy automobile data transmission optimizing system based on the 5G short-slice private network further comprises a communication bus, a communication interface and other components well known to those skilled in the art, and the setting and the functions of the system are known in the art, so that the system is not described in detail herein.
In the context of this patent, the foregoing memory may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, the computer-readable storage medium may be any suitable magnetic or magneto-optical storage medium, such as, for example, resistance change Memory RRAM (Resistive Random Access Memory), dynamic Random Access Memory DRAM (Dynamic Random Access Memory), static Random Access Memory SRAM (Static Random-Access Memory), enhanced dynamic Random Access Memory EDRAM (ENHANCED DYNAMIC Random Access Memory), high-Bandwidth Memory HBM (High-Bandwidth Memory), hybrid storage cube HMC (Hybrid Memory Cube), or the like, or any other medium that may be used to store the desired information and that may be accessed by an application, a module, or both. Any such computer-readable storage media may be part of, or accessible by, or connected to the device. Any of the applications or modules described herein may be implemented using computer-readable/executable instructions that may be stored or otherwise maintained by such computer-readable media.
In the description of the present specification, the meaning of "a plurality", "a number" or "a plurality" is at least two, for example, two, three or more, etc., unless explicitly defined otherwise.
While various embodiments of the present invention have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. Many modifications, changes, and substitutions will now occur to those skilled in the art without departing from the spirit and scope of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in practicing the invention.
Claims (6)
1. The new energy automobile data transmission optimization method based on the 5G short-slice private network is characterized by comprising the following steps of:
Selecting an optimal edge node corresponding to the data of each new energy automobile according to the distance between each new energy automobile and each edge node and the real-time transmission task quantity of each edge node, and transmitting the data of the new energy automobile through the corresponding optimal edge node;
Transmitting data of each new energy automobile through a corresponding optimal edge node; in the real-time transmission process, monitoring the running state of each new energy automobile by using a new energy automobile fault prediction model, and respectively adjusting the data transmission frequency of each new energy automobile according to the running state of each new energy automobile so as to increase the data transmission frequency of the new energy automobile with abnormal running state and reduce the data transmission frequency of the new energy automobile with normal running state, wherein the new energy automobile fault prediction model is used for acquiring the running normal probability and the running abnormal probability of the new energy automobile according to the index data of each new energy automobile;
for a new energy automobile, the method for determining the optimal edge node of the new energy automobile comprises the steps of firstly calculating the mismatching degree of the new energy automobile and each edge node, and selecting the edge node with the smallest mismatching degree as the optimal edge node, wherein the calculation expression of the mismatching degree is as follows:
In the method, in the process of the invention, Representing the degree of mismatch,/>Representing the distance between the ith new energy automobile and the jth edge transmission node,Representing the real-time transmission task quantity of the jth edge node;
If at a certain moment, data of a plurality of new energy automobiles are transmitted through the same edge node at the same time, analyzing the history of data transmission for the edge node to obtain the optimal data transmission quantity of the edge node, calculating the total quantity of the transmissible data of each new energy automobile according to the optimal data transmission quantity and the number of the new energy automobiles transmitting the data through the edge node, and enabling the data of the new energy automobiles transmitted each time not to exceed the total quantity of the corresponding transmissible data;
The calculation expression of the total amount of the transmissible data of the new energy automobile is as follows:
Wherein, Representing the total amount of transmissible data of the ith new energy automobile,/>Representing the optimal data traffic of the jth edge transmission node,/>Representing the number of new energy automobiles transmitted by the jth edge transmission node;
For a new energy automobile, after all index data corresponding to the index data are transmitted once, the index data with the highest priority are transmitted once again;
the adjusting of the data transmission frequency of each new energy automobile comprises the following steps: according to the initial data transmission frequency of the new energy automobile, the normal running probability of the new energy automobile and the abnormal running probability of the new energy automobile, the new data transmission frequency f of the new energy automobile is determined, and the calculation expression is as follows:
In the method, in the process of the invention, Representing the initial transmission frequency,/>Representing the probability of abnormal operation of a new energy automobile output by a neural network,/>And the probability that the new energy automobile output by the neural network runs normally is represented.
2. The method for optimizing data transmission of the new energy automobile based on the 5G short-slice private network according to claim 1, wherein the method for constructing the new energy automobile fault prediction model comprises the following steps:
Collecting operation data of each moment in the history operation process of the new energy automobile, and labeling the operation data of each moment so as to obtain a new energy automobile operation data set; the labels comprise two labels of normal running and abnormal running of the new energy vehicle; the operation data comprise various index data of the new energy automobile;
training the neural network model by using the new energy vehicle running data set until the model reaches the set maximum training times or the loss is smaller than the set loss threshold value, and selecting the optimal model as the new energy vehicle fault prediction model according to the accuracy of model prediction.
3. The method for optimizing data transmission of a new energy automobile based on a 5G short-slice private network according to claim 1, wherein the index data comprises: battery system data, motor data, and vehicle speed and acceleration during operation of the vehicle.
4. The method for optimizing data transmission of new energy vehicles based on the 5G short-slice private network according to claim 1, wherein the method for determining the transmission priority of the index data is as follows: and acquiring the importance degree of each index on the normal operation of the new energy automobile based on the new energy automobile fault prediction model, wherein the higher the importance degree is, the higher the corresponding transmission priority is, and the importance degree of each index on the normal operation of the new energy automobile is acquired through a cam algorithm.
5. The method for optimizing data transmission of a new energy automobile based on a 5G short-slice private network according to claim 1, wherein obtaining the optimal data transmission amount of the edge node comprises:
Clustering the transmission quality of the historical data of the edge nodes, so as to obtain clusters with good transmission quality and clusters with poor transmission quality;
And calculating the average value of the data quantity transmitted each time in the cluster with good transmission quality, thereby obtaining the optimal data transmission quantity of the edge node.
6. The new energy automobile data transmission optimization system based on the 5G short-cut private network comprises a memory and a processor, wherein computer program instructions are stored in the memory, and the new energy automobile data transmission optimization method based on the 5G short-cut private network is characterized in that when the computer program instructions are executed by the processor, the new energy automobile data transmission optimization method based on the 5G short-cut private network is realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410197083.1A CN117768923B (en) | 2024-02-22 | 2024-02-22 | New energy automobile data transmission optimization method and system based on 5G short-cut private network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410197083.1A CN117768923B (en) | 2024-02-22 | 2024-02-22 | New energy automobile data transmission optimization method and system based on 5G short-cut private network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117768923A CN117768923A (en) | 2024-03-26 |
| CN117768923B true CN117768923B (en) | 2024-05-28 |
Family
ID=90310827
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410197083.1A Active CN117768923B (en) | 2024-02-22 | 2024-02-22 | New energy automobile data transmission optimization method and system based on 5G short-cut private network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117768923B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN206181057U (en) * | 2016-08-31 | 2017-05-17 | 西安市地下铁道有限责任公司 | Synthesize bus testing arrangement that calls out stops |
| CN110113376A (en) * | 2019-03-29 | 2019-08-09 | 南京邮电大学 | A kind of Multipath Transmission load balance optimization algorithm based on mobile edge calculations |
| CN112785016A (en) * | 2021-02-20 | 2021-05-11 | 南京领行科技股份有限公司 | New energy automobile maintenance and fault monitoring and diagnosis method based on machine learning |
| CN113411754A (en) * | 2018-05-10 | 2021-09-17 | 华为技术有限公司 | Method for sending message and related equipment |
| CN115052262A (en) * | 2022-06-22 | 2022-09-13 | 东南大学深圳研究院 | Potential game-based vehicle networking computing unloading and power optimization method |
| JP7240691B1 (en) * | 2021-09-08 | 2023-03-16 | 山東大学 | Data drive active power distribution network abnormal state detection method and system |
| CN116193471A (en) * | 2022-12-28 | 2023-05-30 | 电子科技大学 | Edge computing unloading method based on deep reinforcement learning |
| WO2023216457A1 (en) * | 2022-05-11 | 2023-11-16 | 中电信数智科技有限公司 | Method for predicting and positioning abnormity of transmission network between core network and base station |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10298482B2 (en) * | 2017-01-25 | 2019-05-21 | Ringcentral, Inc. | Systems and methods for regulating network resources to improve data-transmission quality |
-
2024
- 2024-02-22 CN CN202410197083.1A patent/CN117768923B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN206181057U (en) * | 2016-08-31 | 2017-05-17 | 西安市地下铁道有限责任公司 | Synthesize bus testing arrangement that calls out stops |
| CN113411754A (en) * | 2018-05-10 | 2021-09-17 | 华为技术有限公司 | Method for sending message and related equipment |
| CN110113376A (en) * | 2019-03-29 | 2019-08-09 | 南京邮电大学 | A kind of Multipath Transmission load balance optimization algorithm based on mobile edge calculations |
| CN112785016A (en) * | 2021-02-20 | 2021-05-11 | 南京领行科技股份有限公司 | New energy automobile maintenance and fault monitoring and diagnosis method based on machine learning |
| JP7240691B1 (en) * | 2021-09-08 | 2023-03-16 | 山東大学 | Data drive active power distribution network abnormal state detection method and system |
| WO2023216457A1 (en) * | 2022-05-11 | 2023-11-16 | 中电信数智科技有限公司 | Method for predicting and positioning abnormity of transmission network between core network and base station |
| CN115052262A (en) * | 2022-06-22 | 2022-09-13 | 东南大学深圳研究院 | Potential game-based vehicle networking computing unloading and power optimization method |
| CN116193471A (en) * | 2022-12-28 | 2023-05-30 | 电子科技大学 | Edge computing unloading method based on deep reinforcement learning |
Non-Patent Citations (2)
| Title |
|---|
| 5G边缘计算和网络切片技术;项弘禹;肖扬文;张贤;朴竹颖;彭木根;;电信科学;20170620(第06期);全文 * |
| 基于深度强化学习的无线网络资源分配算法;李孜恒;孟超;;通信技术;20200810(第08期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117768923A (en) | 2024-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11904875B2 (en) | Adaptive prognostics systems and methods for vehicles | |
| WO2020211356A1 (en) | Relay protection system risk assessment and fault positioning method and apparatus, and device and medium | |
| US10716017B2 (en) | Telecommunications network troubleshooting systems | |
| CN103426056B (en) | Power system weak link identification method based on risk assessment | |
| CN110988596B (en) | Novel active power distribution network fault section positioning method | |
| US20150088835A1 (en) | Facilitating determination of reliability of crowd sourced information | |
| CN110083515A (en) | Quick judgment method, device and the storage medium of slow disk in distributed memory system | |
| CN116860300B (en) | Multi-subnet multi-ECU-oriented vehicle-mounted OTA parallel upgrading method and system | |
| CN111027591B (en) | Node fault prediction method for large-scale cluster system | |
| CN117768923B (en) | New energy automobile data transmission optimization method and system based on 5G short-cut private network | |
| CN114244713B (en) | Resource backup method and device for electric power 5G network slice | |
| CN117807550A (en) | Intelligent quantitative detection method and system for building fire-fighting facilities | |
| Yuan et al. | FedTSE: Low-cost federated learning for privacy-preserved traffic state estimation in IoV | |
| CN113518367B (en) | Fault diagnosis method and system based on service characteristics under 5G network slice | |
| CN116594446B (en) | Temperature control method and system for big data center | |
| CN117290443A (en) | Data layout optimization method of electric energy quality monitoring system based on edge calculation | |
| CN113572639B (en) | Carrier network fault diagnosis method, system, equipment and medium | |
| CN117896163B (en) | Network flow monitoring system | |
| CN110932913A (en) | Self-adaptive service migration method and device based on case base matching | |
| Li et al. | A Trust Evaluation Method Based on Environmental Assessment in the Perception Layer of Internet of Vehicles | |
| Liu et al. | [Retracted] Fault‐Tolerant Secure Routing Based on Trust Evaluation Model in Data Center Networks | |
| Feng et al. | Fault Identification and Analysis of Communication Network Based on Deep Learning | |
| CN118536009B (en) | Power data model construction method and system based on generation type artificial intelligence | |
| CN112260873B (en) | Dynamic network fault diagnosis method under 5G network slice | |
| CN117539728B (en) | Distributed database monitoring realization method, system, device and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |